In this research, we made a detailed vegetation map with 39 wetland plant communities of Shibetsu wetland in the eastern part of Hokkaido, where wetland vegetation has begun to change in recent years, using color aerial photographs taken with a digital camera mounted on a drone (an Unmanned aerial vehicle) in order to conserve its wetland ecosystem. Examining that vegetation map, we characterized the current status of wetland vegetation and analyzed the vegetation change by comparing it with the vegetation survey records conducted in the past.

As a result, Abies sachalinensis, Picea glehnii, Larix kaempferi, Betula platyphylla var. japonica have invaded into the high moor of the Shibetsu wetland and the vegetation has drastically changed. Moreover, Sasa spp. also is recognized to have been widely invading into the high moor. It turns out that some measures to preserve valuable high moor vegetation and the wetland environment should be taken in the near future.

Our country is promoting supporting activities for training players and improving the competitiveness in preparation for international sporting events including Tokyo Olympic Games. Especially recently, one of the supporting activities at present is to utilize high-performance sensing devices for analyzing tactics by measuring the positional data of the players and digitizing their performances. However, sensing devices have not been put to practical use yet because it is hard for the players to wear them during games of various kinds of sports. Therefore, technologies for identifying players by image processing from the video images are the mainstream of the sports information fields. However, they have a problem that the identification accuracy decreases because lots of players are occluded into image data. Thus, in this research, we use multi-cameras from single viewpoint to identify American football players with high accuracy and specify their positions by photographing occlusion points with high zoom magnification, and then applying deep learning of the OpenPose. Finally, we embed the identification results of the OpenPose to the video images taken with low zoom magnification and try to identify players and to analyze their positions.

Plant height, one of the fundamental crop growth parameters, is usually collected by a direct measurement. The authors have developed a method for the estimation of rice plant height by using a short-range LiDAR measurement from above a paddy rice canopy. In this method, the estimated rice plant height is calculated based on the analysis of the vertical distribution of 3D point cloud data, therefore the estimation is affected by foliage abundance and laser incident angle conditions. Plants with similar height but different foliage abundance were observed using a short-range LiDAR from above a paddy rice canopy to examine the influence of the incident angles on rice plant height estimation. The results of the examination showed that the influence of the incident angle condition was similar in different foliage abundance until the maximum tiller number stage. In addition, the estimation of rice plant height was not affected by foliage abundance in a laser incident angle less than 8 degrees which is almost a vertical incident condition.